2 papers
cs.CV2026
Rethinking Detection Calibration: A Coordinate and Direction Perspective
Juyong Lee, Seungjin Jung, Jungmin Lee +2
Deep learning based object detectors require trustworthiness beyond competitive detection performance, but deep neural networks are prone to overconfident predictions, assigning hi…
cs.CV2025
Group-wise Scaling and Orthogonal Decomposition for Domain-Invariant Feature Extraction in Face Anti-Spoofing
Seungjin Jung, Kanghee Lee, Yonghyun Jeong +3
Domain Generalizable Face Anti-Spoofing (DGFAS) methods effectively capture domain-invariant features by aligning the directions (weights) of local decision boundaries across domai…